WorldRuler: Interactive World Modeling under Configurable Rules Paper • 2611.24869 • Published 2 days ago • 18
Game2Player: Scaling Gameplay Experience for Visual Agents through Environment-Player Co-Development Paper • 2611.24154 • Published 2 days ago • 25
PROLA: Principal-Orthogonal Low-rank Adaptation for Predictive Spatiotemporal Weather Downscaling Paper • 2611.11318 • Published 12 days ago • 28
FVScore: Specification-Driven Neuro-Symbolic Video Evaluation Paper • 2611.22673 • Published 3 days ago • 3
In-context Robot Learning Made Simple: A Democratized Recipe for Manipulation Tasks Paper • 2609.38173 • Published Sep 29 • 49
Multi-Agent Egocentric World Model with Fine-Grained Embodied Interaction Paper • 2610.12299 • Published Oct 8 • 55
SuperNav: An Agentic Navigation System for Any Task in Any Scene Paper • 2610.12126 • Published Oct 8 • 78
MiMo-V2.6: Scaling Reinforcement Learning Towards Self-Improvement Paper • 2610.11959 • Published Oct 8 • 83
From Traces to Agentic Worlds: Agentic Language World Models for Interactive Environment Simulation Paper • 2610.06100 • Published Oct 5 • 64
TokenRouter: Efficient Serving System for Token-Level LLM Routing Paper • 2610.12242 • Published Oct 8 • 119
Learn2Play Bench: How Well Do LLM Agents Learn from Experience in Unfamiliar Environments? Paper • 2610.08215 • Published Oct 8 • 41
SWE-MISBEHAVIOR: Benchmarking and Mitigating Boundary Violations in Software Coding Agents Paper • 2610.18206 • Published Oct 13 • 10
VISTA: A Test-Time Self-Improving Video Generation Agent Paper • 2510.15831 • Published Oct 17, 2025 • 24
A^2RD: Agentic Autoregressive Diffusion for Long Video Consistency Paper • 2605.06924 • Published May 7 • 16
Hallucinations Undermine Trust; Metacognition is a Way Forward Paper • 2605.01428 • Published May 2 • 24